Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 111675
    Prev
    Next
    INDEX
    Explanations

    let me know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (or
    -0.09
     ida
    -0.08
     Ndi
    -0.08
     eesm
    -0.08
     инде
    -0.08
     atawa
    -0.08
    hely
    -0.08
     постепенно
    -0.08
     отда
    -0.08
     yayi
    -0.08
    POSITIVE LOGITS
    具体
    0.10
     подробнее
    0.10
    详细
    0.10
     konkr
    0.10
     detall
    0.09
     বিস্তারিত
    0.09
     detailed
    0.09
     વિગ
    0.09
     specifics
    0.09
    詳細
    0.09
    Activations Density 0.022%

    No Known Activations